Corpus classification method and device, computer equipment and storage medium

Abstract

The embodiment of the invention discloses a corpus classification method and device, computer equipment and a storage medium. The method comprises: acquring to-be-classified corpus information; Performing word segmentation processing on the corpus information to generate a word segmentation set, and converting the word segmentation set into a word vector matrix; Inputting the word vector matrix into a corpus classification model; And reading a classification result of the word vector matrix output by the corpus classification model, and recording a classification target represented by the classification result as a classification mark of the corpus information. Due to the fact that the classification corpus model is a neural network model trained to be in a convergence state, information expressed by corpus information expressed by the word vector matrix can be accurately analyzed, then the word vector matrix is classified to obtain a classification result, and the corpus information is classified and marked according to the classification result. And the corpus information is classified through the neural network model, so that the corpus information classification efficiency canbe improved.

Description

technical field [0001] The embodiments of the present invention relate to the field of language processing, in particular, a corpus classification method, device, computer equipment and storage medium. Background technique [0002] Corpus, that is, language material, is the content of linguistic research, and corpus is the basic unit that constitutes a corpus. The corpus stores the language materials that have actually appeared in the actual use of the language; the corpus is the basic resource of language knowledge carried by the computer; the real corpus needs to be processed (analyzed and processed) before it can become a useful resource. [0003] In the existing technology, the classification of corpus has become an important basic research of language processing or AI language interaction. Accurate classification of corpus can accurately grasp the semantics expressed by the corpus, and then execute the instructions represented by the corpus or reply. In the prior art,...

AI Technical Summary

Problems solved by technology

In the prior art, another classification method adopted is to classify and mark the corpus by extracting keywords in the corpus, and to classify the corpus by detecting whether the corpus has the same or similar keywords as the set classification items labeling, but each word has different meanings in different real user corpus contexts, therefore, there is a high error rate in keyword classification

Images